writing-style

writing-style is a skill for Claude Code, Codex from subhansh-dev/agent-maxxing. It costs 23 tokens per session (675 once invoked), scanned A, original, MIT.

A writing guide for making technical text sound natural, direct, specific, and human.

In plain words
What is it for?
Use it when writing documentation, interface text, code comments, reviews, or other developer-facing content.
Why use it?
It helps avoid stiff wording, repetitive sentences, vague advice, and common phrases that make AI-generated text feel generic.

Skill for Claude CodeCodex

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add skills/subhansh-dev/agent-maxxing/writing-style
Any agent
npx skills add subhansh-dev/agent-maxxing --skill writing-style
Clone the repo
git clone --depth 1 https://github.com/subhansh-dev/agent-maxxing

Made for: Claude Code, Codex.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for writing-style

README.md
[![agentmods](https://agentmods.dev/badge/skills/subhansh-dev/agent-maxxing/writing-style.svg)](https://agentmods.dev/skills/subhansh-dev/agent-maxxing/writing-style)
Your own site
<a href="https://agentmods.dev/skills/subhansh-dev/agent-maxxing/writing-style"><img src="https://agentmods.dev/badge/skills/subhansh-dev/agent-maxxing/writing-style.svg" alt="Measured on agentmods" height="20"></a>
Per session 23 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 675 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.00023 $0.00675
Opus 5 $0.00012 $0.00338
Sonnet 5 $0.00005 $0.00135
Haiku 4.5 $0.00002 $0.00068

Measured 4d ago against content hash f00d98a8ad1a, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

writing-style scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

content/writing-style/SKILL.md · 84 lines

How it starts

The opening of the file, as written. The whole thing — 84 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Writing Style Guide — How to Sound Human

Core Rule

Write like you're talking to a smart friend, not presenting to a board of directors.

Voice

  • Direct. Say what you mean. Don't wrap it in cushioning.
  • Opinionated. Have preferences. "This approach is cleaner" beats "this is one possible approach."
  • Specific. "Use clamp() for fluid sizing" beats "consider responsive approaches."
  • Honest. If something is hard, say it's hard. If you're unsure, say so.

Sentence Structure

Vary your rhythm. Short punchy sentences. Then longer ones that take their time getting where they're going, building up context and nuance before arriving at the point. Mix it up.

Don't start every sentence the same way. If three sentences in a row start with "The" or "This" or "I", rewrite.

Use active voice. "The function returns a value" not "a value is returned by the function."

What to Avoid

AI Slop Words

These are dead giveaways. Never use them:

  • serves as, stands as, is a testament to
  • vibrant, rich (figurative), profound, groundbreaking
  • delve, tapestry, landscape (abstract), interplay
  • crucial, pivotal, key, vital, significant
  • Additionally, Moreover, Furthermore
  • It's important to note that
  • I hope this helps!

Filler Phrases

Cut these entirely:

  • "In order to" → "To"
  • "Due to the fact that" → "Because"
  • "At this point in time" → "Now"
  • "The ability to" → just use the verb
  • "It is worth noting that" → just say the thing

Hedging

Don't water everything down:

  • "It could potentially possibly be argued that..." → "This is wrong because..."

Sycophantic Openers

Never start with:

  • "Great question!" / "Absolutely!" / "I'd be happy to help!"
  • "That's an excellent point!"
  • Just answer the question.

Formatting

  • Bold for key terms on first use, not for entire sentences
  • Code blocks for code, not for emphasis
  • Lists for parallel items, not for prose
  • Tables for comparisons, not for single-column data
  • Headers for structure, not for decoration

Read the full file on GitHub · 84 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 84 lines · 23 tokens per session scan A f00d98a8ad1a

Subscribe to this mod's changes

writing-style is a skill published in the GitHub repository subhansh-dev/agent-maxxing (2 stars, last pushed 1mo ago), licensed MIT. It adds 23 tokens to every session and 675 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.